An Energy-Adaptive Elastic Equivariant Transformer Framework for Protein Structure Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Zhongyue, Ma, Runze, Huang, Yanjie, Zheng, Shuangjia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909549185728512
author Zhang, Zhongyue
Ma, Runze
Huang, Yanjie
Zheng, Shuangjia
author_facet Zhang, Zhongyue
Ma, Runze
Huang, Yanjie
Zheng, Shuangjia
contents Structure-informed protein representation learning is essential for effective protein function annotation and \textit{de novo} design. However, the presence of inherent noise in both crystal and AlphaFold-predicted structures poses significant challenges for existing methods in learning robust protein representations. To address these issues, we propose a novel equivariant Transformer-State Space Model(SSM) hybrid framework, termed $E^3$former, designed for efficient protein representation. Our approach uses energy function-based receptive fields to construct proximity graphs and incorporates an equivariant high-tensor-elastic selective SSM within the transformer architecture. These components enable the model to adapt to complex atom interactions and extract geometric features with higher signal-to-noise ratios. Empirical results demonstrate that our model outperforms existing methods in structure-intensive tasks, such as inverse folding and binding site prediction, particularly when using predicted structures, owing to its enhanced tolerance to data deviation and noise. Our approach offers a novel perspective for conducting biological function research and drug discovery using noisy protein structure data.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16996
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Energy-Adaptive Elastic Equivariant Transformer Framework for Protein Structure Representation
Zhang, Zhongyue
Ma, Runze
Huang, Yanjie
Zheng, Shuangjia
Biomolecules
Structure-informed protein representation learning is essential for effective protein function annotation and \textit{de novo} design. However, the presence of inherent noise in both crystal and AlphaFold-predicted structures poses significant challenges for existing methods in learning robust protein representations. To address these issues, we propose a novel equivariant Transformer-State Space Model(SSM) hybrid framework, termed $E^3$former, designed for efficient protein representation. Our approach uses energy function-based receptive fields to construct proximity graphs and incorporates an equivariant high-tensor-elastic selective SSM within the transformer architecture. These components enable the model to adapt to complex atom interactions and extract geometric features with higher signal-to-noise ratios. Empirical results demonstrate that our model outperforms existing methods in structure-intensive tasks, such as inverse folding and binding site prediction, particularly when using predicted structures, owing to its enhanced tolerance to data deviation and noise. Our approach offers a novel perspective for conducting biological function research and drug discovery using noisy protein structure data.
title An Energy-Adaptive Elastic Equivariant Transformer Framework for Protein Structure Representation
topic Biomolecules
url https://arxiv.org/abs/2503.16996